Lessons
Two tracks. Watch, then ask.
Each lesson is a short video, the notes that matter, and a place to ask while you watch. Pick the track that fits where you are. Your progress is saved on this device.
Beginner
What a neural network is, and how it changes its numbers when it is wrong. No code required.
3Blue1Brown
What a neural network is
Grant Sanderson walks through a network that reads handwritten digits. No code. The point is the structure: layers of numbers, weights, and a final guess.
Video · 6 key pointsWatch →
3Blue1Brown
How a network learns
The follow-up. A cost function, then gradient descent: small changes to the weights that reduce error on examples you already labeled.
Video · 6 key pointsWatch →
Manager
What a language model is in practice, and what people mean by generative AI. Enough to ask better questions.
Andrej Karpathy
Large language models, without training one
Andrej Karpathy’s one-hour talk for a general audience. What the model file is, what training cost looked like in 2023, and where the security problems sit. The shape of the explanation still holds.
Video · 7 key pointsWatch →
Google Cloud Tech
What generative AI is
A short Google Cloud lesson. A definition, how this sits next to other machine learning, and the kinds of output people mean when they say generative.
Video · 6 key pointsWatch →